Video Super-Resolution with Convolutional Neural Networks

Convolutional neural networks (CNN) have so far been successfully applied to image super-resolution (SR) as well as other image restoration tasks. In this project, we consider the problem of video super-resolution. We propose a CNN that is trained on both the spatial and the temporal dimensions of videos to enhance their spatial resolution and show extensive comparison to the state-of-the-art video and image super-resolution algorithms.

The software can be found under the project page:
Video Super-Resolution with Convolutional Neural Networks


Description: CalibRT is a MATLAB toolbox that calibrates a color camera with a depth camera. It uses a checkered, square, planar target, and performs the calibration automatically and with minimal user interaction. Please email Ilya Mikhelson (email in Readme file) with any problems, concerns, or suggestions.
The software can be downloaded here: here.

Bayesian Compressive Sensing Using Laplace Priors

In this work, we formulate the CS reconstruction problem from a Bayesian perspective. We utilize a Bayesian model for the CS problem and propose the use of Laplace priors on the basis coefficients in a hierarchical manner
The MATLAB source code for this work can be downloaded from here, which is provided for academic and research purposes. It contains the core algorithm code for fast Bayesian Compressive Sensing using Laplace priors, and an example script to run it.


Blind image restoration

Developed by Cora Beatriz Pérez Ariza and José Manuel Llamas Sánchez under the direction of Prof. Rafael Molina and Prof. Javier Mateos, implements the algorithms in the paper R. Molina, J. Mateos and A. K. Katsaggelos “Blind Deconvolution using a variational approach to parameter, image, and blur estimation,” IEEE Trans. on Image Processing, vol. 15, no. 12, 3715-3727, December 2006.